EHR Algorithms Can Identify Patients with Hypertension, Study Finds | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

EHR Algorithms Can Identify Patients with Hypertension, Study Finds

July 16, 2014
by Gabriel Perna
| Reprints

Parsing electronic health records (EHRs) with algorithms can help researchers identify patients with hypertension, a new study from Northwestern Medicine reveals.

For the study, which appears in the most recent issue of Annals of Family Medicine, researchers looked at patients with previously undiagnosed hypertension, or high blood pressure. They found that of the 1,033 patients who were identified with the EHR algorithms and evaluated, 361 were formally diagnosed with the hypertension and 290 others were diagnosed with related blood pressure conditions such as prehypertension, white-coat hypertension or elevated blood pressure.

"Hypertension is easy to miss if someone is seeing multiple physicians," stated the study's co-author, David W. Baker, M.D., chief of internal medicine and geriatrics at Northwestern Memorial Hospital and Northwestern University Feinberg School of Medicine. "A patient may see one doctor who thinks the blood pressure is due to the patient not feeling well that day and then see another doctor for a different problem who thinks the blood pressure is high because the patient was hurrying to make the appointment. No one puts all of these readings together and realizes a person's blood pressure is always elevated."

The study, "A Technology-Based Quality Innovation to Identify Undiagnosed Hypertension Among Active Primary Care Patients," was broken into two parts. For the first part, researchers identified patients was being at risk for undiagnosed hypertension using the three EHR algorithms and were invited to complete an automated office blood pressure (AOBP) test. The testing was created to eliminate white coat effect, which is when falsely elevated blood pressure results are associated with patients being in the presence of a healthcare provider.

For the second part of the study, additional patients at risk for unidentified hypertension were identified with the same three EHR algorithms and were then observed over the course of two years. They were were contacted by healthcare staff and asked to arrange a follow-up appointment. All of the primary care physicians that participated in the study also received monthly lists of their patients who remained at risk for having hypertension according to the algorithms.

Using the data from this study, researchers conclude that using algorithms to screen EHR data for patients at risk for undiagnosed hypertension may applicable to other commonly undiagnosed chronic diseases.

Read the source article at EurekAlert!

The Health IT Summits gather 250+ healthcare leaders in cities across the U.S. to present important new insights, collaborate on ideas, and to have a little fun - Find a Summit Near You!


See more on